New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Serve] Multiple LB in the same service #4869

Open

cblmemo opened this issue Mar 3, 2025 · 1 comment

Labels

serve

Collaborator

cblmemo commented Mar 3, 2025

In this comment, a user requires multiple LB in one single service. One possible approach would be follow this design:

service:
  ports:
    - 8000,9000 # Indicating there will be one LB for all IP + Port pairs, if Port == 8000 or 9000
    - 10000-10100,7888 # if port in [10000,10100] or port == 7888
    - 7000 # Indicating a LB for all IP:7000

cblmemo added the serve label

cblmemo mentioned this issue

[Serve] Expose multiple ports while using sky serve #3727

Closed

cblmemo changed the title ~~[Serve] Multiple LB~~ [Serve] Multiple LB in the same service

Collaborator Author

cblmemo commented Mar 4, 2025

Alternative:
User provide a dict: {model_name: port}
LB: redirect /model_name to correcponding ports.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment